Developing a Decision Tree Model to Diagnose Polycystic Ovary Syndrome and Evaluating It Using Diverse Machine Learning Techniques

Abstract

Polycystic Ovary Syndrome (PCOS) is a highly concerning condition that can cause significant long-term damage to a woman's health. If left undiagnosed or not caught at an early stage, it can lead to Sterility, syndrome X, obstructive sleep apnea(OSA), major depressive disorder, and even uterine cancer. However, with proper monitoring and treatment, many of these negative effects can be avoided. By utilizing various machine learning methods, an effective decision tree model can be established to assist with early diagnosis and management of PCOS. This model can help women recognize noticeable changes in their bodies and hormone levels and make informed decisions about when to seek medical attention.